Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hardware acceleration and accessibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EnumType
    0.45
    ritte
    0.43
    )=[
    0.42
     isotype
    0.42
     mitigation
    0.42
     doom
    0.42
     разобраться
    0.42
     보험
    0.42
    codone
    0.41
     insurance
    0.40
    POSITIVE LOGITS
     Fleurit
    0.45
     giorni
    0.45
     Unfortunately
    0.44
     jedin
    0.44
     nova
    0.44
     belieb
    0.44
    ൺലൈ
    0.44
    }*/
    0.43
     Jeopardy
    0.43
     erode
    0.43
    Act Density 0.004%

    No Known Activations